Claude Fable 5.2 vs Claude Sonnet 5
Claude Fable 5.2 leads Claude Sonnet 5 by 24.0 points on the Shogo Agent Index. Claude Fable 5.2 wins 15 and Claude Sonnet 5 wins 0 of 15 shared benchmarks. Claude Sonnet 5 is cheaper for agent workloads.
Add more models to this comparison →Pillars
| Pillar | Claude Fable 5.2 | Claude Sonnet 5 |
|---|---|---|
| Agentic coding | 86 | 57 |
| Long-horizon autonomy | 78 | 65 |
| Knowledge-work agents | 67 | 43 |
| Computer use | 77 | 40 |
| Security & context learning | 65 | 51 |
Shared benchmarks
| Benchmark | Claude Fable 5.2 | Claude Sonnet 5 |
|---|---|---|
| APEX-Agentsindex | 80.1% | 54.5% |
| Vending-Bench 2index | $9,628 | $6,378 |
| CursorBenchindex | 60.0% | 34.1% |
| Chess Puzzles | 79.0% | 45.0% |
| CritPt | 35.7% | 16.9% |
| DTBench | 99.2% | 92.5% |
| FrontierMath Tier 4 | 100.0% | 29.3% |
| FrontierMath Tiers 1-3 | 95.1% | 65.6% |
| GPQA Diamond | 96.0% | 90.5% |
| LMCA | 70.6% | 50.0% |
| OTIS Mock AIME | 99.7% | 94.7% |
| ProofBench | 100.0% | 77.0% |
| SciCode | 67.7% | 54.3% |
| SimpleBench | 94.9% | 60.6% |
| SimpleQA Verified | 94.0% | 33.7% |
Specs and price
| Claude Fable 5.2 | Claude Sonnet 5 | |
|---|---|---|
| Agent Index | 76.4 (#1) | 52.4 (#32) |
| Agent $/M | $3.21 | $0.92 |
| Input / output $/M | $8.00 / $40.00 | $2.00 / $10.00 |
| Context | 1M | 1M |
| Released | Nov 9, 2026 | Jun 30, 2026 |
| Weights | Closed | Closed |
| API hosts | 4 | 5 |
Don’t pick one. Route.
Shogo can run Claude Fable 5.2 and Claude Sonnet 5 side by side and send each step of an agent to the one that’s cheaper for it.
Try both in Shogo